Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3765 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1055801 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.8474. Min Act: -0.0000

Data Index: 328101 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.8201. Min Act: 0.0002

Data Index: 803886 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.7616. Min Act: 0.0001

Data Index: 117406 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.7349. Min Act: -0.0000

Data Index: 340005 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1151718 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.6762. Min Act: -0.0000

Data Index: 865855 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4509. Min Act: 0.0001

Data Index: 301255 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1141091 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4754. Min Act: -0.0000

Data Index: 575847 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.5534. Min Act: -0.0000

Data Index: 671120 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4197. Min Act: 0.0001

Data Index: 1296507 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4109. Min Act: 0.0001

Data Index: 783447 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.4124. Min Act: -0.0000

Data Index: 651778 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3762. Min Act: -0.0000

Data Index: 312399 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3740. Min Act: 0.0001

Data Index: 306424 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3526. Min Act: -0.0000

Data Index: 517869 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3518. Min Act: 0.0000

Data Index: 1170537 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1164941 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.8792. Min Range: -1.8792

Max Act: 1.3372. Min Act: 0.0000

Data Index: 904467 (C4 (Web Text))

Max Activating Token Index: 832